R Notebook

library(tidyverse)

Registered S3 method overwritten by 'rvest':
  method            from
  read_xml.response xml2
── Attaching packages ────────────────────────────────────────────────────────────────── tidyverse 1.2.1 ──
✔ ggplot2 3.1.0       ✔ purrr   0.3.2  
✔ tibble  2.1.1       ✔ dplyr   0.8.0.1
✔ tidyr   0.8.3       ✔ stringr 1.4.0  
✔ readr   1.3.1       ✔ forcats 0.4.0  
── Conflicts ───────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()

library(plotly)

Registered S3 method overwritten by 'data.table':
  method           from
  print.data.table     
Registered S3 methods overwritten by 'htmltools':
  method               from         
  print.html           tools:rstudio
  print.shiny.tag      tools:rstudio
  print.shiny.tag.list tools:rstudio
Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio

Attaching package: ‘plotly’

The following object is masked from ‘package:ggplot2’:

    last_plot

The following object is masked from ‘package:stats’:

    filter

The following object is masked from ‘package:graphics’:

    layout

getStarts <- function(d){
  s = d %>% select(Stage, Nodes, Time, Tasks) %>% 
    group_by(Stage, Nodes) %>% 
    summarise(Start=min(Time), Tasks=min(Tasks)) %>% arrange(Start)
  return(s)
}

RESEARCH_HOME = "/home/and/Documents/PhD/Research"
lines = readLines(paste0(RESEARCH_HOME, "/Scripts/Misc/tmp/monitor2.txt"))
lines = lines[grepl("|", lines)]
monitor = as_tibble(lines) %>%
  separate(value, into=c("Timestamp", "Time", "ID", "Nodes", "Cores", "Node", "Stage", "RDDs", "Tasks", "Times", "Load"), sep="\\|") %>%
  separate(ID, into=c(NA, NA, "ID"), sep="-") %>%
  select(ID, Time, Nodes, Stage, RDDs, Tasks, Load) %>%
  mutate(Time=as.numeric(Time), RDDs=as.numeric(RDDs), Tasks=as.numeric(Tasks), Load=as.numeric(Load)) %>%
  group_by(ID, Time, Nodes, Stage) %>% summarise(RDDs=mean(RDDs), Tasks=mean(Tasks), Load=mean(Load))

Calling `as_tibble()` on a vector is discouraged, because the behavior is likely to change in the future. Use `tibble::enframe(name = NULL)` instead.
This warning is displayed once per session.

d = monitor %>% filter(ID == "0051" || ID == "0052" || ID == "0053") %>% ungroup %>% 
  select(Time, Tasks, Nodes, Stage) %>% 
  mutate(Stage=factor(Stage), Nodes=factor(Nodes), Time=floor(Time*10.0)/10.0) %>% 
  group_by(Nodes, Stage, Time) %>%
  summarise(Tasks=mean(Tasks)) %>%
  arrange(Time, Tasks) 
head(d, n=30)

p = ggplot(data = d, aes(x = Time, y = Tasks, group = 1)) +
  geom_line(aes(color = Nodes, linetype = Nodes)) +
  geom_point(data = getStarts(d), aes(x=Start, y=Tasks, group=Nodes, color=Nodes
                                      , text = paste(Stage,"<br>Start:",Start,"<br>",Tasks)))

Ignoring unknown aesthetics: text

ggplotly(p, tooltip = c("text"))